Registry › Compare › Herdr vs Rtk

Herdr vs Rtk

Herdr leads on trust: 65.7/100 (Grade B) against 64.9/100 (Grade C), a 0.8-point gap. Herdr leads on supply-chain integrity; Rtk leads on adoption.

B Herdr 65.7

the runtime your coding agents live on

herdrdev/herdr · #54 overall · #54 Agent Skills · coverage C (2/5)

Choose Herdr if supply-chain integrity matters most.

  • +1.8Safety / Integrity: 85% of recent commits signed, against 44%
C Rtk 64.9

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

rtk-ai/rtk · #62 overall · #62 Agent Skills · coverage C (2/5)

Choose Rtk if adoption matters most.

  • +0.6Adoption: 84.2k GitHub stars against 45.2k

Where they differ

11.1
Safety / IntegrityHerdr +1.8
9.3
13.2
TransparencyRtk +0.1
13.3
11.2
AdoptionRtk +0.6
11.8
-0.6
Runtime calibrationRtk +0.3
-0.3

2 dimensions identical: Identity 10.8 · Maintenance 20.0 · Full evidence table

An independent, evidence-based trust comparison of Herdr and Rtk, two Agent Skills projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal Herdrherdrdev/herdr Rtkrtk-ai/rtk
HVTrust score 65.7 64.9
Evidence grade B C
Coverage grade C C
Overall rank #54 #62
Rank in Agent Skills #54 #62
GitHub stars 45.2k 84.2k
Last updated today today
Build provenance No No
OSSF Scorecard 5.5 / 10 5.7 / 10
License Apache-2.0 Apache-2.0
Downloads — —
Trust dimensions (points earned)
Safety / integrity / 25 11.1 9.3
Identity & provenance / 18 10.8 10.8
Transparency / 17 13.2 13.3
Maintenance / 20 20.0 20.0
Adoption / 20 11.2 11.8
Runtime capability surface (full matrix)
MCP server — —
External providers — —
Requires API keys No No
Plugin surface extensions plugins
Provenance drift — —
Open in the live compare tool → Herdr profile Rtk profile More Agent Skills →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.4 →